Abstract
The learning capability of a network-based computation model named “Algorithmically Transitive Network (ATN)” is extensively studied using symbolic regression problems. To represent a variety of functions uniformly, the ATN’s topological structure is designed in the form of a truncated power series or a Padé approximant. Since the Padé approximation has better convergence properties than the Taylor expansion, the ATN with the Padé can construct an algebraic function with a relatively small number of parameters. The ATN learns with the standard back-propagation algorithm which optimizes intra-network parameters by the steepest descent method. Numerical experiments with benchmark problems show that the ATN in the form of a Padé approximant has better learning capability than linear regression analysis in a power series, the standard multi-layered neural network with the back-propagation learning, the support vector machine using the radial basis function as kernel, or the simple genetic programming.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
aiSee: Commercial software for visualizing graphs with various algorithms such as rubberband. http://www.aisee.com/
Baker, G.A.: Essentials of Padé Approximants. Academic Press, New York (1975)
Barron, R.L.: Adaptive transformation networks for modelling, prediction, and control. In: IEEE Systems, Man, and Cybernetics Group Annual Symposium Record, pp. 254–263 (1971)
Bishop, C.M.: Pattern Recognition And Machine Learning: Information Science and Statistics. Springer, Berlin (2006)
Burges, C.: A tutorial on support vector machines for pattern recognition. Data Min. Knowl. Disc. 2, 21–167 (1998)
Dennis, J.B.: Data flow supercomputer. IEEE Comput. 13(11), 48–56 (1980)
Downing, K.L.: Reinforced genetic programming. Genet. Program. Evolvable Mach. 2(3), 259–288 (2001)
Funahashi, K.: On the approximate realization of continuous mappings by neural networks. Neural Netw. 2(3), 183–192 (1989)
Haykin, S.: Neural networks and learning machines. Prentice-Hall, Upper Saddle River (2009)
Iba, H., de Garis, H., Sato, T.: A numerical approach to genetic programming for system identification. Evol. Comput. 3(4), 417–452 (1995)
Iba, H.: Multi-agent reinforcement learning with genetic programming. In: Koza, J.R., et al. (eds): Genetic Programming 1998: Proceedings of the Third Annual Conference (GP-98), pp. 167–172 (1998)
Ivakhnenko, A.G.: Polynomial theory of complex systems. IEEE Trans. Sys. Man Cyber. SMC-1, 364–378 (1971)
Kawato, M., Furukawa, K., Suzuki, R.: A hierarchical neural-network model for control and learning of voluntary movement. Biol. Cybern. 57, 169–185 (1987)
Keijzer, M.: Improving symbolic regression with interval arithmetic and linear scaling. In: Ryan, C., Soule, T., Keijzer, M., Tsang, E.P.K., Poli, R., Costa, E. (eds.) EuroGP 2003. LNCS, vol. 2610, pp. 70–82. Springer, Heidelberg (2003)
Koza, J.R.: Genetic Programming: on the Programming of Computers by Means of Natural Selection. MIT Press, Boston (1992)
Ljung, L.: System Identification: Theory for the User. Prentice Hall, Upper Saddle River (1998)
Mabu, S., Hirasawa, K., Hu, J.: A graph-based evolutionary algorithm: genetic network programming (GNP) and its extension using reinforcement learning. Evol. Comput. 15(3), 369–398 (2007)
Mehta, B., Schaal, S.: Forward models in visuomotor control. J. Neurophysiol. 88, 942–953 (2002)
Miller, J.F.: An empirical study of the efficiency of learning boolean functions using a cartesian genetic programming approach. In: Banzhaf, W., et al. (eds.) Proceedings of the Genetic and Evolutionary Computation Conference, vol. 2, pp. 1135–1142. Morgan Kaufmann (1999)
Miller, J.F., Smith, S.L.: Redundancy and computational efficiency in cartesian genetic programming. IEEE Trans. Evol. Comput. 10(2), 167–174 (2006)
Nikolaev, N.Y., Iba, H.: Regularization approach to inductive genetic programming. IEEE Trans. Evol. Comput. 5(4), 359–375 (2001)
Otani, M., Taji, K., Uno, Y.: Motion adaptation with iterative control using inverse-dynamics model. (Japan.) Inst. Electron. Inf. Commun. Eng. J. D J95-D(2), 305–313 (2012)
Pagie, L., Hogeweg, P.: Evolutionary consequences of coevolving targets. Evol. Comput. 5(4), 401–418 (1997)
Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning representations by back-propagating errors. Nature 323, 533–536 (1986)
Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning internal representations by error propagation. In: McClelland, J.L., Rumelhart, D.E. (eds.) The PDP Research Group: Parallel Distributed Processing, vol. 1, pp. 45–76. MIT Press, Cambridge (1986)
Schölkopf, B., Smola, A.J., Williamson, R.C., Bartlett, P.L.: New support vector algorithms. Neural Comput. 12(5), 1207–1245 (2000)
Sejnowski, T.J., Rosenberg, C.R.: Parallel networks that learn to pronounce English text. Complex Syst. 1, 145–168 (1987)
Sharp, J.A. (ed.): Data Flow Computing: Theory and Practice. Ablex Publishing Corp, Norwood (1992)
Skomorokhov, A.O.: Adaptive learning networks in APL2. In: Proceedings of the international conference on APL (APL ’93), pp. 219–229. ACM, New York (1993)
Soares, C., Brazdil, P.B.: Selecting parameters of SVM using meta-learning and kernel matrix-based meta-features. In: Proceedings of the 2006 ACM Symposium on Applied Computing (SAC ’06), pp. 564–568. ACM, New York (2006)
Suzuki, H.: A network cell with molecular agents that divides from centrosome signals. BioSystems 94, 118–125 (2008)
Suzuki, H., Ohsaki, H., Sawai, H.: A network-based computational model with learning. In: Calude, C.S., Hagiya, M., Morita, K., Rozenberg, G., Timmis, J. (eds.) Unconventional Computation. LNCS, vol. 6079, pp. 193–193. Springer, Heidelberg (2010)
Suzuki, H., Ohsaki, H., Sawai H.: Algorithmically transitive network: a new computing model that combines artificial chemistry and information-communication engineering. In: Proceedings of the 24th Annual Conference of Japanese Society for Artificial Intelligence (JSAI), 2H1-OS4-5 (Japanese, 2010)
Suzuki, H., Ohsaki, H., Sawai, H.: An agent-based neural computational model with learning. Frontiers in Neuroscience. Conference Abstract: Neuroinformatics (2010). doi:10.3389/conf.fnins.2010.13.00021
Suzuki, H., Ohsaki, H., Sawai, H.: Algorithmically transitive network: a self-organizing data-flow network with learning. In: Suzuki, J., Nakano, T. (eds.) BIONETICS 2010. LNICST, vol. 87, pp. 59–73. Springer, Heidelberg (2012)
Suzuki, H.: Padé network: a parametric machine Learning system for regression. In: Proceedings of the 22nd Annual Conference of Japanese Neural Network Society, P2–20 (2012)
Teller, A., Veloso, M.: PADO: Learning tree-structured algorithm for orchestration into an object recognition system. Carnegie Mellon University Technical report, CMU-CS-95-101 (1995)
Tennenhouse, D.L., Wetherall, D.J.: Towards an active network architecture. ACM Comput. Commun. Rev. 26(2), 5–18 (1996)
Uy, N.Q., Hoai, N.X., O’Neill, M., McKay, R.I., Galván-López, E.: Semantically-based crossover in genetic programming: application to real-valued symbolic regression. Genet. Program. Evolvable Mach. 12(2), 91–119 (2011)
Vladislavleva, E.J., Smits, G.F., den Hertog, D.: Order of nonlinearity as a complexity measure for models generated by symbolic regression via pareto genetic programming. IEEE Trans. Evol. Comput. 13(2), 333–349 (2009)
Werbos, P.J.: The roots of backpropagation: From ordered derivatives to neural networks and political forecasting. Adaptive and Learning Systems for Signal Processing, Communications and Control Series. Wiley-Interscience, New York (1994)
Wuytack, L. (ed.): Padé Approximation and Its Applications: Proceedings of a Conference Held in Antwerp, Belgium. Lecture Notes in Mathematics. Springer, Heidelberg (1979)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Institute for Computer Sciences, Social Informatics and Telecommunications Engineering
About this paper
Cite this paper
Suzuki, H. (2014). Algorithmically Transitive Network: Learning Padé Networks for Regression. In: Di Caro, G., Theraulaz, G. (eds) Bio-Inspired Models of Network, Information, and Computing Systems. BIONETICS 2012. Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, vol 134. Springer, Cham. https://doi.org/10.1007/978-3-319-06944-9_11
Download citation
DOI: https://doi.org/10.1007/978-3-319-06944-9_11
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-06943-2
Online ISBN: 978-3-319-06944-9
eBook Packages: Computer ScienceComputer Science (R0)